A Machine Learning Approach to TCP Throughput Prediction

Abstract

<i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TCP throughput prediction</i> is an important capability for networks where multiple paths exist between data senders and receivers. In this paper, we describe a new lightweight method for TCP throughput prediction. Our predictor uses Support Vector Regression (SVR); prediction is based on both prior file transfer history and measurements of simple path properties. We evaluate our predictor in a laboratory setting where ground truth can be measured with perfect accuracy. We report the performance of our predictor for <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">oracular</i> and <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">practical</i> measurements of path properties over a wide range of traffic conditions and transfer sizes. For bulk transfers in heavy traffic using <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">oracular</i> measurements, TCP throughput is predicted within 10% of the actual value 87% of the time, representing nearly a threefold improvement in accuracy over prior history-based methods. For <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">practical</i> measurements of path properties, predictions can be made within 10% of the actual value nearly 50% of the time, approximately a 60% improvement over history-based methods, and with much lower measurement traffic overhead. We implement our predictor in a tool called <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PathPerf</i> , test it in the wide area, and show that <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PathPerf</i> predicts TCP throughput accurately over diverse wide area paths.